{"id":"W3191474316","doi":"10.3390/dj9080094","title":"Evaluating Classification Consistency of Oral Lesion Images for Use in an Image Classification Teaching Tool","year":2021,"lang":"en","type":"article","venue":"Dentistry Journal","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Faculty of Medicine and Dentistry, University of Alberta; University of Alberta","keywords":"Kappa; Rubric; Consistency (knowledge bases); Artificial intelligence; Cohen's kappa; Medicine; Inter-rater reliability; Lesion; Pattern recognition (psychology); Computer science; Mathematics; Machine learning; Statistics; Pathology; Mathematics education","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001671514,0.00009716994,0.0002742127,0.00008332839,0.0001314528,0.0001349468,0.00007021064,0.0001039156,0.00006063295],"category_scores_gemma":[0.0506029,0.00009085354,0.000132459,0.0001055283,0.00006272948,0.0003123239,0.00001990329,0.000405139,0.000004451712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009220833,"about_ca_system_score_gemma":0.0003394104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001460138,"about_ca_topic_score_gemma":0.00001183982,"domain_scores_codex":[0.9982796,0.0002516793,0.0007245892,0.0002370618,0.0003309989,0.0001760555],"domain_scores_gemma":[0.9960499,0.002586297,0.00037229,0.00025769,0.0006108027,0.0001229537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002677391,0.001187264,0.318764,0.00007620878,0.00003729447,0.0002400928,0.0001266808,0.00001259443,0.4866099,0.0006329598,0.001390404,0.1906549],"study_design_scores_gemma":[0.00331509,0.0002855396,0.9738824,0.001419911,0.0001714345,0.001107289,0.0008429529,0.01242988,0.005846197,0.0004906477,0.0000958411,0.0001127635],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9838969,0.0001325966,0.01481675,0.0005124352,0.0003012437,0.0001704522,0.00001948352,0.00001365501,0.0001365161],"genre_scores_gemma":[0.9098781,0.00006067858,0.08943866,0.00007720548,0.0001330508,0.000009868263,0.0001402395,0.00001450193,0.0002477218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6551184,"threshold_uncertainty_score":0.9573942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2608180206976614,"score_gpt":0.490187083475301,"score_spread":0.2293690627776396,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}